Merge branch 'libbpf: uprobe name-based attach followups'

Alan Maguire says:

====================

Follow-up series to [1] to address some suggestions from Andrii to
improve parsing and make it more robust (patches 1, 2) and to improve
validation of u[ret]probe firing by validating expected argument
and return values (patch 3).

[1] https://lore.kernel.org/bpf/164903521182.13106.12656654142629368774.git-patchwork-notify@kernel.org/

Changes since v1:
- split library name, auto-attach parsing into separate patches (Andrii, patches 1, 2)
- made str_has_sfx() static inline, avoided repeated strlen()s by storing lengths,
  used strlen() instead of strnlen() (Andrii, patch 1)
- fixed sscanf() arg to use %li, switched logging to use "prog '%s'" format,
  used direct strcmp() on probe_type instead of prefix check (Andrii, patch 2)
- switched auto-attach tests to log parameter/return values to be checked by
  user-space side of tests. Needed to add pid filtering to avoid capturing
  stray malloc()s (Andrii, patch 3)
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

2 files changed, 45 insertions, 49 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1111e9d16e01..016ecdd1c3e1 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10766,7 +10766,7 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz)
 	const char *search_paths[3] = {};
 	int i;
 
-	if (strstr(file, ".so")) {
+	if (str_has_sfx(file, ".so") || strstr(file, ".so.")) {
 		search_paths[0] = getenv("LD_LIBRARY_PATH");
 		search_paths[1] = "/usr/lib64:/usr/lib";
 		search_paths[2] = arch_specific_lib_paths();
@@ -10913,60 +10913,45 @@ err_out:
 static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts);
-	char *func, *probe_name, *func_end;
-	char *func_name, binary_path[512];
-	unsigned long long raw_offset;
-	size_t offset = 0;
-	int n;
+	char *probe_type = NULL, *binary_path = NULL, *func_name = NULL;
+	int n, ret = -EINVAL;
+	long offset = 0;
 
 	*link = NULL;
 
-	opts.retprobe = str_has_pfx(prog->sec_name, "uretprobe");
-	if (opts.retprobe)
-		probe_name = prog->sec_name + sizeof("uretprobe") - 1;
-	else
-		probe_name = prog->sec_name + sizeof("uprobe") - 1;
-	if (probe_name[0] == '/')
-		probe_name++;
-
-	/* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */
-	if (strlen(probe_name) == 0)
-		return 0;
-
-	snprintf(binary_path, sizeof(binary_path), "%s", probe_name);
-	/* ':' should be prior to function+offset */
-	func_name = strrchr(binary_path, ':');
-	if (!func_name) {
-		pr_warn("section '%s' missing ':function[+offset]' specification\n",
+	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.]+%li",
+		   &probe_type, &binary_path, &func_name, &offset);
+	switch (n) {
+	case 1:
+		/* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */
+		ret = 0;
+		break;
+	case 2:
+		pr_warn("prog '%s': section '%s' missing ':function[+offset]' specification\n",
+			prog->name, prog->sec_name);
+		break;
+	case 3:
+	case 4:
+		opts.retprobe = strcmp(probe_type, "uretprobe") == 0;
+		if (opts.retprobe && offset != 0) {
+			pr_warn("prog '%s': uretprobes do not support offset specification\n",
+				prog->name);
+			break;
+		}
+		opts.func_name = func_name;
+		*link = bpf_program__attach_uprobe_opts(prog, -1, binary_path, offset, &opts);
+		ret = libbpf_get_error(*link);
+		break;
+	default:
+		pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name,
 			prog->sec_name);
-		return -EINVAL;
-	}
-	func_name[0] = '\0';
-	func_name++;
-	n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset);
-	if (n < 1) {
-		pr_warn("uprobe name '%s' is invalid\n", func_name);
-		return -EINVAL;
-	}
-	if (opts.retprobe && offset != 0) {
-		free(func);
-		pr_warn("uretprobes do not support offset specification\n");
-		return -EINVAL;
-	}
-
-	/* Is func a raw address? */
-	errno = 0;
-	raw_offset = strtoull(func, &func_end, 0);
-	if (!errno && !*func_end) {
-		free(func);
-		func = NULL;
-		offset = (size_t)raw_offset;
+		break;
 	}
-	opts.func_name = func;
+	free(probe_type);
+	free(binary_path);
+	free(func_name);
 
-	*link = bpf_program__attach_uprobe_opts(prog, -1, binary_path, offset, &opts);
-	free(func);
-	return libbpf_get_error(*link);
+	return ret;
 }
 
 struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog,
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index dd0d4ccfa649..080272421f6c 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -103,6 +103,17 @@
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
+/* suffix check */
+static inline bool str_has_sfx(const char *str, const char *sfx)
+{
+	size_t str_len = strlen(str);
+	size_t sfx_len = strlen(sfx);
+
+	if (sfx_len <= str_len)
+		return strcmp(str + str_len - sfx_len, sfx);
+	return false;
+}
+
 /* Symbol versioning is different between static and shared library.
  * Properly versioned symbols are needed for shared library, but
  * only the symbol of the new version is needed for static library.